I wrote both a brute-force and a divide-and-conquer implementation of the Max Subarray problem in Python. Tests are run by drawing a random sample of integers.
When the length of the input array is large, the assert in __main__ fails because the recursive algorithm does not return the correct answer. However, the two algorithms DO agree when the array is less than 10 elements long (this is approximate, and the actual size of the failed input varies on each execution). The issue does not seem to be related to even or odd array lengths, but it does appear to be related to how the array is indexed.
Sorry if I'm missing something stupid, but why does the recursive algorithm stop returning the correct output when the input array starts getting larger?
# Subarray solutions are represented by an array in the form
# [lower_bound, higher_bound, sum]
from sys import maxsize
import random
import time
# Brute force implementation (THETA(n^2))
def bf_max_subarray(A):
biggest = -maxsize - 1
left = 0
right = 0
for i in range(0, len(A)):
sum = 0
for j in range(i, len(A)):
sum += A[j]
if sum > biggest:
biggest = sum
left = i
right = j
return [left, right, biggest]
# Part of divide-and-conquer solution
def cross_subarray(A, l, m, r):
lsum = -maxsize - 1
rsum = -maxsize - 1
lbound = 0
rbound = 0
tempsum = 0
for i in range(m, l-1, -1):
tempsum += A[i]
if tempsum > lsum:
lsum = tempsum
lbound = i
tempsum = 0
for j in range(m+1, r+1):
tempsum += A[j]
if tempsum > rsum:
rsum = tempsum
rbound = j
return [lbound, rbound, lsum + rsum]
# Recursive solution
def rec_max_subarray(A, l, r):
# Base case: array of one element
if (l == r):
return [l, r, A[l]]
else:
m = (l+r)//2
left = rec_max_subarray(A, l, m)
right = rec_max_subarray(A, m+1, r)
cross = cross_subarray(A, l, m, r)
# Returns the array representing the subarray with the maximum sum.
return max([left, right, cross], key=lambda i:i[2])
if __name__ == "__main__":
for i in range(1, 101):
A = random.sample(range(-i*2, i), i)
start = time.clock()
bf = bf_max_subarray(A)
bf_time = time.clock() - start
start = time.clock()
dc = rec_max_subarray(A, 0, len(A)-1)
dc_time = time.clock() - start
assert dc == bf # Make sure the algorithms agree.
The subarray with the maximum sum is represented by an array of the form [left_bound, right_bound, sum].
But thanks toreturn max([left, right, cross], key=lambda i:i[2]), rec_max_subarray returns the correct maximum sum for A, but risks returning indicies that do not match the indicies returned in bf_max_subarray. My error was assuming that the boundaries of a subarray with the maximum sum would be unique.
The solution is to either fix the criteria that selects a subarray, or just to assert the equality of the sums using assert dc[2] == bf[2].
Related
This question already has answers here:
FibFrog Codility Problem - Optimising for Performance
(2 answers)
Closed last year.
I'm trying to solve the Codility FibFrog problem and I came up with the following solution:
def jumps_from(position, fb, A):
paths = set([])
for i in fb:
newPos = position + i
if newPos == len(A):
return set([-1])
elif newPos < len(A):
if A[newPos] == 1:
paths.add(newPos)
else: break
return paths
def solution(A):
if len(A) < 3: return 1
fibonaccis = fibonacci(len(A))
if len(A) + 1 in fibonaccis: return 1
paths = set([-1])
steps = 0
while True:
paths = set([idx for pos in paths for idx in jumps_from(pos, fibonaccis, A)])
if len(paths) == 0: return -1
if -1 in paths:
return steps + 1
steps += 1
return steps
def fibonacci(N):
arr = [0] * (N + 2)
arr[1] = 1
for i in range(2, N + 2):
arr[i] = arr[i-1] + arr[i-2]
return dict.fromkeys(arr[2:], 1)
Codility detects the runtime of this as O(N * log(N) ** N).
Codility Report: https://app.codility.com/demo/results/trainingJV7YAC-G3B/
I'm comparing this with the following solution, which scores 100% on Codility, and has runtime O(N * log(N)):
def gen_fib(n):
fn = [0,1]
i = 2
s = 2
while s < n:
s = fn[i-2] + fn[i-1]
fn.append(s)
i+=1
return fn
def new_paths(A, n, last_pos, fn):
"""
Given an array A of len n.
From index last_pos which numbers in fn jump to a leaf?
returns list: set of indexes with leaves.
"""
paths = []
for f in fn:
new_pos = last_pos + f
if new_pos == n or (new_pos < n and A[new_pos]):
paths.append(new_pos)
return paths
def solution(A):
n = len(A)
if n < 3:
return 1
# A.append(1) # mark final jump
fn = sorted(gen_fib(100000)[2:]) # Fib numbers with 0, 1, 1, 2.. clipped to just 1, 2..
# print(fn)
paths = set([-1]) # locate all the leaves that are one fib jump from the start position.
jump = 1
while True:
# Considering each of the previous jump positions - How many leaves from there are one fib jump away
paths = set([idx for pos in paths for idx in new_paths(A, n, pos, fn)])
# no new jumps means game over!
if not paths:
break
# If there was a result in the new jumps record that
if n in paths:
return jump
jump += 1
return -1
I'm not sure why my solution differs in runtime, since the approach is exactly the same - compute all the indices you can jump to from -1, and then compute all the indices you can jump to from the new positions, until you get to the other side of the river, or no new positions can be found.
Please refer to the first point in my previous answer.
If len(A) = 100000, you are calculating 100003 fibonacci numbers, while we only need fibonacci numbers which are less than 100k, which would be <30 of them.
The current fibonacci function is still returning N fibonacci numbers instead of just returning fibonacci numbers which are less than N. For N=100k, it should be just 25 numbers instead of over 100k.
Please update your fibonacci function to this -
def fibonacci(N):
arr = [1, 1]
while arr[-1] < N:
arr.append(arr[-1] + arr[-2])
return dict.fromkeys(arr[1:], 1)
I just ran a test locally, and looks like your fibonacci function takes ~1 sec to generate the first 100k fibonacci numbers, and that's the reason it might be failing the performance test, even though the rest of your code is optimal. I think you should be able to clear it with the required performance limits after correcting the fibonacci function.
I know how to check if the number can be represented as the sum of two squares with a brute-force approach.
def sumSquare( n) :
i = 1
while i * i <= n :
j = 1
while(j * j <= n) :
if (i * i + j * j == n) :
print(i, "^2 + ", j , "^2" )
return True
j = j + 1
i = i + 1
return False
But how to do it for n distinct positive integers. So the question would be:
Function which checks if the number can be written as sum of 'n' different squares
I have some examples.
For e.g.
is_sum_of_squares(18, 2) would be false because 18 can be written as the sum of two squares (3^2 + 3^2) but they are not distinct.
(38,3) would be true because 5^2+3^2+2^2 = 38 and 5!=3!=2.
I can't extend the if condition for more values. I think it could be done with recursion, but I have problems with it.
I found this function very useful since it finds the number of squares the number can be split into.
def findMinSquares(n):
T = [0] * (n + 1)
for i in range(n + 1):
T[i] = i
j = 1
while j * j <= i:
T[i] = min(T[i], 1 + T[i - j * j])
j += 1
return T[n]
But again I can't do it with recursion. Sadly I can't wrap my head around it. We started learning it a few weeks ago (I am in high school) and it is so different from the iterative approach.
Recursive approach:
def is_sum_of_squares(x, n, used=None):
x_sqrt = int(x**0.5)
if n == 1:
if x_sqrt**2 == x:
return used.union([x_sqrt])
return None
used = used or set()
for i in set(range(max(used, default=0)+1, int((x/n)**0.5))):
squares = is_sum_of_squares(x-i**2, n-1, used.union([i]))
if squares:
return squares
return None
Quite a compelling exercise. I have attempted solving it using recursion in a form of backtracking. Start with an empty list, run a for loop to add numbers to it from 1 to max feasible (square root of target number) and for each added number continue with recursion. Once the list reaches the required size n, validate the result. If the result is incorrect, backtrack by removing the last number.
Not sure if it is 100% correct though. In terms of speed, I tried it on the (1000,13) input and the process finished reasonably fast (3-4s).
def is_sum_of_squares(num, count):
max_num = int(num ** 0.5)
return backtrack([], num, max_num, count)
def backtrack(candidates, target, max_num, count):
"""
candidates = list of ints of max length <count>
target = sum of squares of <count> nonidentical numbers
max_num = square root of target, rounded
count = desired size of candidates list
"""
result_num = sum([x * x for x in candidates]) # calculate sum of squares
if result_num > target: # if sum exceeded target number stop recursion
return False
if len(candidates) == count: # if candidates reach desired length, check if result is valid and return result
result = result_num == target
if result: # print for result sense check, can be removed
print("Found: ", candidates)
return result
for i in range(1, max_num + 1): # cycle from 1 to max feasible number
if candidates and i <= candidates[-1]:
# for non empty list, skip numbers smaller than the last number.
# allow only ascending order to eliminate duplicates
continue
candidates.append(i) # add number to list
if backtrack(candidates, target, max_num, count): # next recursion
return True
candidates.pop() # if combination was not valid then backtrack and remove the last number
return False
assert(is_sum_of_squares(38, 3))
assert(is_sum_of_squares(30, 3))
assert(is_sum_of_squares(30, 4))
assert(is_sum_of_squares(36, 1))
assert not(is_sum_of_squares(35, 1))
assert not(is_sum_of_squares(18, 2))
assert not(is_sum_of_squares(1000, 13))
A common algorithm for solving the problem of finding the median of two sorted arrays of size m and n is to:
Run binary search to adjust "a cut" of the smaller array in two halves. When doing so, we adjust the cut of the larger array to make sure the total number of elements on the first halves of both arrays equals the total number of elements in the second halves of both arrays, which is a pre-condition for splitting both arrays around the median.
The binary search shifts the cuts left or right until all elements on the left halves <= all elements on the right halves.
At the end of the procedure, we can readily compute the median with a basic comparison of the elements on the boundary of the cuts of both arrays.
While I understand at a high level the algorithm, I'm not sure I understand why one needs to do the calculation on the smaller array, and adjust the larger array, as opposed to the other way around.
Here's a video explaining the algorithm, but the author doesn't explain exactly why we use the smaller array to drive the binary search.
I'm also including below Python code that is supposed to solve the problem, mostly to make the post self-contained, even if it's not well documented.
def median(A, B):
m, n = len(A), len(B)
if m > n:
## Making sure that A refers to the smaller array
A, B, m, n = B, A, n, m
if n == 0:
raise ValueError
imin, imax, half_len = 0, m, (m + n + 1) / 2
while imin <= imax:
i = (imin + imax) / 2
j = half_len - i
if i < m and B[j-1] > A[i]:
# i is too small, must increase it
imin = i + 1
elif i > 0 and A[i-1] > B[j]:
# i is too big, must decrease it
imax = i - 1
else:
# i is perfect
if i == 0: max_of_left = B[j-1]
elif j == 0: max_of_left = A[i-1]
else: max_of_left = max(A[i-1], B[j-1])
if (m + n) % 2 == 1:
return max_of_left
if i == m: min_of_right = B[j]
elif j == n: min_of_right = A[i]
else: min_of_right = min(A[i], B[j])
return (max_of_left + min_of_right) / 2.0
By enforcing m <= n, we make sure both i and j are always non-negative.
Also, we are able to reduce some redundant boundary checks in the while loop when working with i and j.
Take the first if condition in the while loop as an example, the code checks for i < m before accessing A[i], but why wouldn't it also check for j-1 >= 0 before accessing B[j-1]? This is because i falls into [0, m], and j = (m + n + 1) / 2 - i, so when i is the largest, j is the smallest.
When i < m, j = (m + n + 1)/2 - i > (m + n + 1)/2 - m = n/2 - m/2 + 1/2 >= 0. So j must be positive when i < m, and j - 1 >= 0.
Similarly, in the second if condition in the while loop, when i > 0, j is guaranteed to be less than n.
To verify this idea, you can try removing the size check and swap logic at the top, and run through below example input, in which A is longer than B.
[1,2,3,4,6]
[5]
Imagine you're trying to allocate some fixed resources (e.g. n=10) over some number of territories (e.g. t=5). I am trying to find out efficiently how to get all the combinations where the sum is n or below.
E.g. 10,0,0,0,0 is good, as well as 0,0,5,5,0 etc., while 3,3,3,3,3,3 is obviously wrong.
I got this far:
import itertools
t = 5
n = 10
r = [range(n+1)] * t
for x in itertools.product(*r):
if sum(x) <= n:
print x
This brute force approach is incredibly slow though; there must be a better way?
Timings (1000 iterations):
Default (itertools.product) --- time: 40.90 s
falsetru recursion --- time: 3.63 s
Aaron Williams Algorithm (impl, Tony) --- time: 0.37 s
Possible approach follows. Definitely would use with caution (hardly tested at all, but the results on n=10 and t=5 look reasonable).
The approach involves no recursion. The algorithm to generate partitions of a number n (10 in your example) having m elements (5 in your example) comes from Knuth's 4th volume. Each partition is then zero-extended if necessary, and all the distinct permutations are generated using an algorithm from Aaron Williams which I have seen referred to elsewhere. Both algorithms had to be translated to Python, and that increases the chance that errors have crept in. The Williams algorithm wanted a linked list, which I had to fake with a 2D array to avoid writing a linked-list class.
There goes an afternoon!
Code (note your n is my maxn and your t is my p):
import itertools
def visit(a, m):
""" Utility function to add partition to the list"""
x.append(a[1:m+1])
def parts(a, n, m):
""" Knuth Algorithm H, Combinatorial Algorithms, Pre-Fascicle 3B
Finds all partitions of n having exactly m elements.
An upper bound on running time is (3 x number of
partitions found) + m. Not recursive!
"""
while (1):
visit(a, m)
while a[2] < a[1]-1:
a[1] -= 1
a[2] += 1
visit(a, m)
j=3
s = a[1]+a[2]-1
while a[j] >= a[1]-1:
s += a[j]
j += 1
if j > m:
break
x = a[j] + 1
a[j] = x
j -= 1
while j>1:
a[j] = x
s -= x
j -= 1
a[1] = s
def distinct_perms(partition):
""" Aaron Williams Algorithm 1, "Loopless Generation of Multiset
Permutations by Prefix Shifts". Finds all distinct permutations
of a list with repeated items. I don't follow the paper all that
well, but it _possibly_ has a running time which is proportional
to the number of permutations (with 3 shift operations for each
permutation on average). Not recursive!
"""
perms = []
val = 0
nxt = 1
l1 = [[partition[i],i+1] for i in range(len(partition))]
l1[-1][nxt] = None
#print(l1)
head = 0
i = len(l1)-2
afteri = i+1
tmp = []
tmp += [l1[head][val]]
c = head
while l1[c][nxt] != None:
tmp += [l1[l1[c][nxt]][val]]
c = l1[c][nxt]
perms.extend([tmp])
while (l1[afteri][nxt] != None) or (l1[afteri][val] < l1[head][val]):
if (l1[afteri][nxt] != None) and (l1[i][val]>=l1[l1[afteri][nxt]][val]):
beforek = afteri
else:
beforek = i
k = l1[beforek][nxt]
l1[beforek][nxt] = l1[k][nxt]
l1[k][nxt] = head
if l1[k][val] < l1[head][val]:
i = k
afteri = l1[i][nxt]
head = k
tmp = []
tmp += [l1[head][val]]
c = head
while l1[c][nxt] != None:
tmp += [l1[l1[c][nxt]][val]]
c = l1[c][nxt]
perms.extend([tmp])
return perms
maxn = 10 # max integer to find partitions of
p = 5 # max number of items in each partition
# Find all partitions of length p or less adding up
# to maxn or less
# Special cases (Knuth's algorithm requires n and m >= 2)
x = [[i] for i in range(maxn+1)]
# Main cases: runs parts fn (maxn^2+maxn)/2 times
for i in range(2, maxn+1):
for j in range(2, min(p+1, i+1)):
m = j
n = i
a = [0, n-m+1] + [1] * (m-1) + [-1] + [0] * (n-m-1)
parts(a, n, m)
y = []
# For each partition, add zeros if necessary and then find
# distinct permutations. Runs distinct_perms function once
# for each partition.
for part in x:
if len(part) < p:
y += distinct_perms(part + [0] * (p - len(part)))
else:
y += distinct_perms(part)
print(y)
print(len(y))
Make your own recursive function which do not recurse with an element unless it's possible to make a sum <= 10.
def f(r, n, t, acc=[]):
if t == 0:
if n >= 0:
yield acc
return
for x in r:
if x > n: # <---- do not recurse if sum is larger than `n`
break
for lst in f(r, n-x, t-1, acc + [x]):
yield lst
t = 5
n = 10
for xs in f(range(n+1), n, 5):
print xs
You can create all the permutations with itertools, and parse the results with numpy.
>>> import numpy as np
>>> from itertools import product
>>> t = 5
>>> n = 10
>>> r = range(n+1)
# Create the product numpy array
>>> prod = np.fromiter(product(r, repeat=t), np.dtype('u1,' * t))
>>> prod = prod.view('u1').reshape(-1, t)
# Extract only permutations that satisfy a condition
>>> prod[prod.sum(axis=1) < n]
Timeit:
>>> %%timeit
prod = np.fromiter(product(r, repeat=t), np.dtype('u1,' * t))
prod = prod.view('u1').reshape(-1, t)
prod[prod.sum(axis=1) < n]
10 loops, best of 3: 41.6 ms per loop
You could even speed up the product computation by populating combinations directly in numpy.
You could optimize the algorithm using Dynamic Programming.
Basically, have an array a, where a[i][j] means "Can I get a sum of j with the elements up to the j-th element (and using the jth element, assuming you have your elements in an array t (not the number you mentioned)).
Then you can fill the array doing
a[0][t[0]] = True
for i in range(1, len(t)):
a[i][t[i]] = True
for j in range(t[i]+1, n+1):
for k in range(0, i):
if a[k][j-t[i]]:
a[i][j] = True
Then, using this info, you could backtrack the solution :)
def backtrack(j = len(t)-1, goal = n):
print j, goal
all_solutions = []
if j == -1:
return []
if goal == t[j]:
all_solutions.append([j])
for i in range(j-1, -1, -1):
if a[i][goal-t[j]]:
r = backtrack(i, goal - t[j])
for l in r:
print l
l.append(j)
all_solutions.append(l)
all_solutions.extend(backtrack(j-1, goal))
return all_solutions
backtrack() # is the answer
I'm reading the Introduction to Algorithms and trying to finish the exercise in the book.
In Exercise 4.1-3
4.1-3
Implement both the brute-force and recursive algorithms for the maximum-subarray problem on your own computer. What problem size n0 gives the crossover
point at which the recursive algorithm beats the brute-force algorithm? Then,
change the base case of the recursive algorithm to use the brute-force algorithm
whenever the problem size is less than n0. Does that change the crossover point?
I wrote the two algorithms according to the book's pseudo-code. However, there must be something wrong with my code because the second one, which is designed to be Theta(n*lgn) and supposed to run faster, always runs slower than the first Theta(n**2) one. My codes is shown below.
def find_maximum_subarray_bf(a): #bf for brute force
p1 = 0
l = 0 # l for left
r = 0 # r for right
max_sum = 0
for p1 in range(len(a)-1):
sub_sum = 0
for p2 in range(p1, len(a)):
sub_sum += a[p2]
if sub_sum > max_sum:
max_sum = sub_sum
l = p1
r = p2
return l, r, max_sum
def find_maximum_subarray_dc(a): #dc for divide and conquer
# subfunction
# given an arrary and three indics which can split the array into a[l:m]
# and a[m+1:r], find out a subarray a[i:j] where l \leq i \less m \less j \leq r".
# according to the definition above, the target subarray must
# be combined by two subarray, a[i:m] and a[m+1:j]
# Growing Rate: theta(n)
def find_crossing_max(a, l, r, m):
# left side
# ls_r and ls_l indicate the right and left bound of the left subarray.
# l_max_sum indicates the max sum of the left subarray
# sub_sum indicates the sum of the current computing subarray
ls_l = 0
ls_r = m-1
l_max_sum = None
sub_sum = 0
for j in range(m+1)[::-1]: # adding elements from right to left
sub_sum += a[j]
if sub_sum > l_max_sum:
l_max_sum = sub_sum
ls_l = j
# right side
# rs_r and rs_l indicate the right and left bound of the left subarray.
# r_max_sum indicates the max sum of the left subarray
# sub_sum indicates the sum of the current computing subarray
rs_l = m+1
rs_r = 0
r_max_sum = None
sub_sum = 0
for j in range(m+1,len(a)):
sub_sum += a[j]
if sub_sum > r_max_sum:
r_max_sum = sub_sum
rs_r = j
#combine
return (ls_l, rs_r, l_max_sum+r_max_sum)
# subfunction
# Growing Rate: should be theta(nlgn), but there is something wrong
def recursion(a,l,r): # T(n)
if r == l:
return (l,r,a[l])
else:
m = (l+r)//2 # theta(1)
left = recursion(a,l,m) # T(n/2)
right = recursion(a,m+1,r) # T(n/2)
crossing = find_crossing_max(a,l,r,m) # theta(n)
if left[2]>=right[2] and left[2]>=crossing[2]:
return left
elif right[2]>=left[2] and right[2]>=crossing[2]:
return right
else:
return crossing
#back to master function
l = 0
r = len(a)-1
return recursion(a,l,r)
if __name__ == "__main__":
from time import time
a = [100,-10,1,2,-1,4,-6,2,5]
a *= 2**10
time0 = time()
find_maximum_subarray_bf(a)
time1 = time()
find_maximum_subarray_dc(a)
time2 = time()
print "function 1:", time1-time0
print "function 2:", time2-time1
print "ratio:", (time1-time0)/(time2-time1)
First, a mistake in the brute-force:
for p1 in range(len(a)-1):
that should be range(len(a)) [or xrange], as is, it wouldn't find the maximum subarray of [-12,10].
Now, the recursion:
def find_crossing_max(a, l, r, m):
# left side
# ls_r and ls_l indicate the right and left bound of the left subarray.
# l_max_sum indicates the max sum of the left subarray
# sub_sum indicates the sum of the current computing subarray
ls_l = 0
ls_r = m-1
l_max_sum = None
sub_sum = 0
for j in range(m+1)[::-1]: # adding elements from right to left
You are checking all the indices to 0, but you should only check the indices to l. Instead of constructing the range list and reversing it, use xrange(m,l-1,-1)
sub_sum += a[j]
if sub_sum > l_max_sum:
l_max_sum = sub_sum
ls_l = j
For the sum to the right, the analogue holds, you should only check indices to r, so xrange(m+1,r+1).
Further, your intitial values for the sums resp. indices for the maximum subarray are dubious for the left part, and wrong for the right.
For the left part, we start with an empty sum but must include a[m]. That can be done by setting l_max_sum = None initially, or by setting l_max_sum = a[m] and letting j omit the index m. Either way, the initial value for ls_l should not be 0, and for ls_r it shouldn't be m-1. ls_r must be m, and ls_l should start as m+1 if the initial value for l_max_sum is None, and as m if l_max_sum starts as a[m].
For the right part, r_max_sum must start as 0, and rs_r should better start as m (though that isn't really important, it would only give you the wrong indices). If none of the sums on the right is ever non-negative, the right sum should be 0 and not the largest of the negative sums.
In recursion, we have a bit of duplication in
left = recursion(a,l,m) # T(n/2)
the sums including a[m] have already been treated or majorised in find_crossing_max, so that could be
left = recursion(a,l,m-1)
But then one would have to also treat the possibility r < l in recursion, and the repetition is small, so I'll let that stand.
Since you always traverse the entire list in find_crossing_max, and that is called O(n) times, your divide-and-conquer implementation is actually O(n²) too.
If the range checked in find_crossing_max is restricted to [l,r], as it should be, you have (approximately) 2^k calls on ranges of length n/2^k, 0 <= k <= log_2 n, for a total cost of O(n*log n).
With these changes (and some random array generation),
def find_maximum_subarray_bf(a): #bf for brute force
p1 = 0
l = 0 # l for left
r = 0 # r for right
max_sum = 0
for p1 in xrange(len(a)):
sub_sum = 0
for p2 in xrange(p1, len(a)):
sub_sum += a[p2]
if sub_sum > max_sum:
max_sum = sub_sum
l = p1
r = p2
return l, r, max_sum
def find_maximum_subarray_dc(a): #dc for divide and conquer
# subfunction
# given an arrary and three indices which can split the array into a[l:m]
# and a[m+1:r], find out a subarray a[i:j] where l \leq i \less m \less j \leq r".
# according to the definition above, the target subarray must
# be combined by two subarray, a[i:m] and a[m+1:j]
# Growing Rate: theta(n)
def find_crossing_max(a, l, r, m):
# left side
# ls_r and ls_l indicate the right and left bound of the left subarray.
# l_max_sum indicates the max sum of the left subarray
# sub_sum indicates the sum of the current computing subarray
ls_l = m+1
ls_r = m
l_max_sum = None
sub_sum = 0
for j in xrange(m,l-1,-1): # adding elements from right to left
sub_sum += a[j]
if sub_sum > l_max_sum:
l_max_sum = sub_sum
ls_l = j
# right side
# rs_r and rs_l indicate the right and left bound of the left subarray.
# r_max_sum indicates the max sum of the left subarray
# sub_sum indicates the sum of the current computing subarray
rs_l = m+1
rs_r = m
r_max_sum = 0
sub_sum = 0
for j in range(m+1,r+1):
sub_sum += a[j]
if sub_sum > r_max_sum:
r_max_sum = sub_sum
rs_r = j
#combine
return (ls_l, rs_r, l_max_sum+r_max_sum)
# subfunction
# Growing Rate: theta(nlgn)
def recursion(a,l,r): # T(n)
if r == l:
return (l,r,a[l])
else:
m = (l+r)//2 # theta(1)
left = recursion(a,l,m) # T(n/2)
right = recursion(a,m+1,r) # T(n/2)
crossing = find_crossing_max(a,l,r,m) # theta(r-l+1)
if left[2]>=right[2] and left[2]>=crossing[2]:
return left
elif right[2]>=left[2] and right[2]>=crossing[2]:
return right
else:
return crossing
#back to master function
l = 0
r = len(a)-1
return recursion(a,l,r)
if __name__ == "__main__":
from time import time
from sys import argv
from random import randint
alen = 100
if len(argv) > 1:
alen = int(argv[1])
a = [randint(-100,100) for i in xrange(alen)]
time0 = time()
print find_maximum_subarray_bf(a)
time1 = time()
print find_maximum_subarray_dc(a)
time2 = time()
print "function 1:", time1-time0
print "function 2:", time2-time1
print "ratio:", (time1-time0)/(time2-time1)
We get something like we should expect:
$ python subarrays.py 50
(3, 48, 1131)
(3, 48, 1131)
function 1: 0.000184059143066
function 2: 0.00020382
ratio: 0.902923976608
$ python subarrays.py 100
(29, 61, 429)
(29, 61, 429)
function 1: 0.000745058059692
function 2: 0.000561952590942
ratio: 1.32583792957
$ python subarrays.py 500
(35, 350, 3049)
(35, 350, 3049)
function 1: 0.0115859508514
function 2: 0.00170588493347
ratio: 6.79175401817
$ python subarrays.py 1000
(313, 572, 3585)
(313, 572, 3585)
function 1: 0.0537149906158
function 2: 0.00334000587463
ratio: 16.082304233
$ python osubarrays.py 10000
(901, 2055, 4441)
(901, 2055, 4441)
function 1: 4.20316505432
function 2: 0.0381460189819
ratio: 110.186204655